Spaces:
Build error
Build error
File size: 3,272 Bytes
46a75d7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
import os
from trainer import Trainer, TrainerArgs
from TTS.config import BaseAudioConfig, BaseDatasetConfig
from TTS.tts.configs.fast_speech_config import FastSpeechConfig
from TTS.tts.datasets import load_tts_samples
from TTS.tts.models.forward_tts import ForwardTTS
from TTS.tts.utils.text.tokenizer import TTSTokenizer
from TTS.utils.audio import AudioProcessor
from TTS.utils.manage import ModelManager
output_path = os.path.dirname(os.path.abspath(__file__))
# init configs
dataset_config = BaseDatasetConfig(
formatter="ljspeech",
meta_file_train="metadata.csv",
# meta_file_attn_mask=os.path.join(output_path, "../LJSpeech-1.1/metadata_attn_mask.txt"),
path=os.path.join(output_path, "../LJSpeech-1.1/"),
)
audio_config = BaseAudioConfig(
sample_rate=22050,
do_trim_silence=True,
trim_db=60.0,
signal_norm=False,
mel_fmin=0.0,
mel_fmax=8000,
spec_gain=1.0,
log_func="np.log",
ref_level_db=20,
preemphasis=0.0,
)
config = FastSpeechConfig(
run_name="fast_speech_ljspeech",
audio=audio_config,
batch_size=32,
eval_batch_size=16,
num_loader_workers=8,
num_eval_loader_workers=4,
compute_input_seq_cache=True,
compute_f0=False,
run_eval=True,
test_delay_epochs=-1,
epochs=1000,
text_cleaner="english_cleaners",
use_phonemes=True,
phoneme_language="en-us",
phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
precompute_num_workers=8,
print_step=50,
print_eval=False,
mixed_precision=False,
max_seq_len=500000,
output_path=output_path,
datasets=[dataset_config],
)
# compute alignments
if not config.model_args.use_aligner:
manager = ModelManager()
model_path, config_path, _ = manager.download_model("tts_models/en/ljspeech/tacotron2-DCA")
# TODO: make compute_attention python callable
os.system(
f"python TTS/bin/compute_attention_masks.py --model_path {model_path} --config_path {config_path} --dataset ljspeech --dataset_metafile metadata.csv --data_path ./recipes/ljspeech/LJSpeech-1.1/ --use_cuda true"
)
# INITIALIZE THE AUDIO PROCESSOR
# Audio processor is used for feature extraction and audio I/O.
# It mainly serves to the dataloader and the training loggers.
ap = AudioProcessor.init_from_config(config)
# INITIALIZE THE TOKENIZER
# Tokenizer is used to convert text to sequences of token IDs.
# If characters are not defined in the config, default characters are passed to the config
tokenizer, config = TTSTokenizer.init_from_config(config)
# LOAD DATA SAMPLES
# Each sample is a list of ```[text, audio_file_path, speaker_name]```
# You can define your custom sample loader returning the list of samples.
# Or define your custom formatter and pass it to the `load_tts_samples`.
# Check `TTS.tts.datasets.load_tts_samples` for more details.
train_samples, eval_samples = load_tts_samples(
dataset_config,
eval_split=True,
eval_split_max_size=config.eval_split_max_size,
eval_split_size=config.eval_split_size,
)
# init the model
model = ForwardTTS(config, ap, tokenizer)
# init the trainer and 🚀
trainer = Trainer(
TrainerArgs(), config, output_path, model=model, train_samples=train_samples, eval_samples=eval_samples
)
trainer.fit()
|